Re: st: Re: asclogit with panel data

[Klaus Pforr <klaus.pforr@mzes.uni-mannheim.de>]

<>

and again, it should be possible to model alternative spefivic covariate 
sets by using coefficient constraints. This will definitely be very 
complex, and you should take care of what you do, otherwise your results 
will be a mess.

klaus


Am 20.12.2010 17:44, schrieb Klaus Pforr:
> Dear K.,
>
> another ado, that could possibly be helpful is the "mixed conditional 
> logit" by martin elff
> http://www.martin-elff.net/software/mclogit/. Is is basically a mlogit 
> with random effects.
> I don't know of anything else, that is available and ready to use.
>
> best
>
> klaus
>
> Am 20.12.2010 17:35, schrieb Kamyar Baradaran:
> > Dear Klaus,
> >
> > Thanks for your reply. Would you please give me any hint on what to do
> > if I have more alternatives? I have 4 choices (in fact three choices
> > and one "none" category if none of the three choices has been selected
> > in the specific year)
> >
> > Thanks a lot.
> > K.
> > *
> > *   For searches and help try:
> > *   http://www.stata.com/help.cgi?search
> > *   http://www.stata.com/support/statalist/faq
> > *   http://www.ats.ucla.edu/stat/stata/


--
__________________________________

Klaus Pforr
MZES AB - A
Universität Mannheim
D - 68131 Mannheim
Tel:  +49-621-181 2801 (nachmittags)
fax:  +49-621-181 2803
URL:  http://www.mzes.uni-mannheim.de

Besucheranschrift: A5, Raum A312
__________________________________

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/